This Article 
 Bibliographic References 
 Add to: 
On Seeing Spaghetti: Self-Adjusting Piecewise Toroidal Recognition of Flexible Extruded Objects
February 1995 (vol. 17 no. 2)
pp. 136-157

Abstract— We present a model for flexible extruded objects, such as wires, tubes, or grommets, and demonstrate a novel, self-adjusting, seven-dimensional Hough transform that derives their diameter and three-space curved axes from position and surface normal information. The method is purely local and is inexpensive to compute. The model considers such objects as piecewise toroidal, and decomposes the seven parameters of a torus into three nested subspaces, the structures of which counteract the errors implicit in the analysis of objects of great size and/or small curvature. We believe it is the first example of a parameter space structure designed to cluster ill-conditioned hypotheses together so that they can be easily detected and ignored. This work complements existing shape-from-contour approaches for analyzing tori: It uses no edge information, and it does not require the solution of high-degree non-linear equations by iterative techniques. Most of the results, including the conditions for the existence of more than one solution (phantom “anti-tori), have been verified using a symbolic mathematical analysis system. We present, in the environment of the IBM ConVEx system, robust results on both synthetic CAD-CAM range data (the hasp of a lock), and actual range data (a knotted piece of coaxial cable), and discuss several system tuning issues.

[1] D.H. Ballard,“Parameter nets: a theory of low level vision,” Proc. 7th Int’l Joint Conf. On Artificial Intelligence, Aug. 1981, pp. 1068-1078.
[2] R.P. Blanford,“Dynamically quantized pyramids for Hough vote collection,” Univ. of Washington, Dept. Computer Science Technical Report #87-03-08, March26, 1987.
[3] R.M. Bolle, personal correspondence.
[4] T. E. Boult, personal correspondence.
[5] A. Califano,“Feature recognition using correlated information contained in multiple neighborhoods,” Proc. 7th Nat’l Conf. on Artificial Intelligence, July 1988, pp. 831-836.
[6] A. Califano,R.M. Bolle,, and R.W. Taylor,“Generalized neighborhoods: a new approach to complex feature extraction,” IEEE Conf. on Computer Vision and Pattern Recognition, Nov. 1988.
[7] M.P. DoCarmo,Differential Geometry of Curves and Surfaces, New Jersey: Prentice-Hall, 1976.
[8] J.A. Feldman and D.H. Ballard,“Connectionist models and their properties,” Cognitive Science, vol. 6, pp. 205-254, 1981.
[9] P.V.C. Hough,Methods and Means for Recognizing Complex Patterns, U.S. Patent 3069654, 1962.
[10] R.D. Jenks,R.S. Sutor,, and S.M. Watt,“Scratchpad II: an abstract datatype system for mathematical computation,” IBM Technical Report RC12327, Nov. 1986.
[11] J. R. Kender and R. Kjeldsen,“On seeing spaghetti: a radius-finding transform for flexible extruded objects,” IBM Technical Report RC16576, Feb. 1991.
[12] R. Kjeldsen,R.M. Bolle,A. Califano,, and R.W. Taylor,“A homogeneous framework for visual recognition,” Proc. 11th Int’l Joint Conf. on Artificial Intelligence, Aug. 1989, pp. 1578-1584.
[13] D.J. Kriegman and J. Ponce, "On Recognizing and Positioning Curve 3-D Objects From Image Contours," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, pp. 1,127-1,137, Dec. 1990.
[14] V.F. Leavers, "The Dynamic Generalized Hough Transform: Its Relationship to the Probabilistic Hough Transforms and an Application to the Concurrent Detection of Circles and Ellipses," CVGIP: Image Understanding, vol. 56, no. 3, pp. 381-398, Nov. 1992.
[15] J. O’Rourke,“Dynamically quantized spaces for focusing the Hough transform,” Proc. of 7th Int’l Joint Conf. on Artificial Intelligence, pp. 737-739, 1981.
[16] D. Sabbah,“Computing with connections in visual recognition of origami objects,” Cognitive Science, vol. 9, no. 1, pp. 25-50, Jan.-March 1985.
[17] D. Sabbah and R.M. Bolle,“Extraction of surface parameters from depth maps viewing planes and quadrics of revolution,” Proc. SPIE Conf. Intelligent Robots and Computer Vision, Oct. 1986, pp. 222-232.
[18] D.J. Struik,Lectures on Classical Differential Geometry, Addison-Wesley, 1961.
[19] Technical Arts Corporation,100X 3D Scanner: User’s Manual Application Programming Guide,Redmond, Wash., 1986.

Index Terms:
Torus recognition, flexible extruded objects, self-adjusting Hough transform, parameter space decomposition, range data.
John R. Kender, Rick Kjeldsen, "On Seeing Spaghetti: Self-Adjusting Piecewise Toroidal Recognition of Flexible Extruded Objects," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 2, pp. 136-157, Feb. 1995, doi:10.1109/34.368174
Usage of this product signifies your acceptance of the Terms of Use.